EP3326109A1 - System und verfahren zur bereitstellung eines rezeptes - Google Patents
System und verfahren zur bereitstellung eines rezeptesInfo
- Publication number
- EP3326109A1 EP3326109A1 EP16747866.8A EP16747866A EP3326109A1 EP 3326109 A1 EP3326109 A1 EP 3326109A1 EP 16747866 A EP16747866 A EP 16747866A EP 3326109 A1 EP3326109 A1 EP 3326109A1
- Authority
- EP
- European Patent Office
- Prior art keywords
- food
- image data
- determining
- recipe
- candidate
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
- 238000000034 method Methods 0.000 title claims abstract description 57
- 235000013305 food Nutrition 0.000 claims abstract description 157
- 239000004615 ingredient Substances 0.000 claims abstract description 15
- 230000006870 function Effects 0.000 claims description 32
- 238000004519 manufacturing process Methods 0.000 claims description 12
- 230000014509 gene expression Effects 0.000 claims description 10
- 239000005428 food component Substances 0.000 claims description 7
- 235000012041 food component Nutrition 0.000 claims description 7
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 230000007613 environmental effect Effects 0.000 claims description 3
- 230000004044 response Effects 0.000 claims description 3
- 238000012706 support-vector machine Methods 0.000 claims description 3
- 239000000306 component Substances 0.000 description 3
- 235000021186 dishes Nutrition 0.000 description 3
- 230000001419 dependent effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000010191 image analysis Methods 0.000 description 2
- 240000008415 Lactuca sativa Species 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 235000015278 beef Nutrition 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000007717 exclusion Effects 0.000 description 1
- 238000003703 image analysis method Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 235000013372 meat Nutrition 0.000 description 1
- 235000021188 national dish Nutrition 0.000 description 1
- 235000014594 pastries Nutrition 0.000 description 1
- 238000011045 prefiltration Methods 0.000 description 1
- 235000012045 salad Nutrition 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 235000012046 side dish Nutrition 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/68—Food, e.g. fruit or vegetables
Definitions
- the invention relates to a (in particular computer-implemented) method and a corresponding system for determining a recipe. Especially on vacation trips it can happen that you eat ready-made food that you do not know.
- a method for determining a prescription for already prepared or pre-prepared food is described.
- the method may be performed by a processor, such as the processor of an electronic device, such as a smartphone, or a computer.
- the already made Nah typically comprises a variety of different ingredients which are processed as part of a manufacturing process to produce the food.
- the food may have been cooked, in particular cooked, fried, grilled and / or baked.
- the recipe to be identified may display a variety of ingredients for making a food, as well as quantities for the variety of ingredients.
- the recipe to be determined may indicate process steps of a food manufacturing process.
- the recipe to be determined should correspond with the highest possible probability to the recipe used for the production of the already produced food.
- the method includes determining image data indicative of the food already prepared.
- the (especially digital) image data can be determined from a photograph of the food already produced.
- the image data may comprise individual pixels or pixels of a photograph of the foodstuff.
- the method comprises determining a recipe in dependence on the image data.
- a prescription or recipe suggestion that was used with a certain probability for the production of the already produced food can be efficiently determined. Possibly.
- a relevancy value for the identified recipe may be determined and displayed to indicate to the user the likelihood that the identified recipe has been used to make the food already prepared.
- Determining a recipe may include determining (at least) a food candidate based on the image data.
- a food candidate can be determined which, with a certain probability, corresponds to the already produced food.
- the food candidate may be determined from a plurality of (possibly predetermined) food candidates that corresponds to the already produced food with the relatively highest probability (relative to the other candidates of the plurality of food candidates).
- the recipe, which a user as provided a prescription for the pre-prepared food can then be a prescription for making the food candidate.
- this recipe may be taken from a recipe database, where the recipe database for a variety of food candidates includes a corresponding variety of recipes.
- the method may include determining a plurality of food candidates. Furthermore, a corresponding multiplicity of relevance values can be determined for the multiplicity of food candidates. In doing so, the relevance score of a food candidate may indicate a likelihood that the food candidate corresponds to the food already prepared. Furthermore, a plurality of recipes for the plurality of food candidates may be determined (e.g., by accessing the recipe database). A variety of possible recipes for the already produced food can then be provided (and possibly displayed). The plurality of recipes may be provided depending on the corresponding plurality of relevance values (e.g., sorted by decreasing relevance values). By determining a large number of possible recipes, the robustness of the determination of a recipe can be further increased.
- Determining a food candidate may include analyzing the image data to determine an expression of at least one image data feature of the food.
- the image data features may be e.g. a color, a texture, a size, a consistency and / or a shape of the food (or a specific food component) represented in the image data.
- the occurrences of a multiplicity of image data features are determined and combined in a feature vector.
- a food candidate can then be determined as a function of the expression of the at least one image data feature (or of the feature vector). This will enable a robust identification of a probable food candidate for the food already prepared.
- determining a food candidate may include determining an assignment function configured to assign different food candidates to different occurrences of the at least one image data feature (or feature vector, respectively).
- the assignment function may include, for example, a cluster algorithm, a support vector machine and / or a neural network.
- the assignment function may have been learned based on training data, wherein the training data typically indicates a corresponding plurality of actual occurrences of the at least one image data feature (or feature vector) for a plurality of actual foods.
- the food candidate can then be determined as a function of or using the assignment function.
- a trained assignment function enables the robust determination of a probable food candidate for the food already prepared.
- the method may further comprise determining feedback on the determined recipe.
- the feedback indicates to what extent the determined recipe matches the food represented in the image data.
- the feedback may indicate an assessment by a user as to whether or not the recipe has been used to prepare the already-prepared food.
- the assignment function can then be adjusted depending on the feedback.
- the recognition rate of recipes can be further increased.
- the method may further include determining metadata for the image data.
- the metadata may include location information indicating where the image data was acquired.
- the metadata may include time information indicating when the image data was acquired.
- the recipe can then be determined depending on the metadata.
- the recognition rate of recipes can be further increased.
- a pre-selection of potential food candidates can be made to reduce the number of potential food candidates to the food candidates that might be relevant at all in view of the metadata.
- the metadata may be taken into account by selecting the assignment function used for the determination of one or more food candidates, depending on the metadata, from a plurality of assignment functions. For example, different assignment functions can be provided for different locations (eg countries, regions, cities, possibly restaurants).
- the metadata can be taken into account by determining an expression of at least one metadata feature based on the metadata.
- the at least one metadata feature may be part of a feature vector that includes one or more image data features and one or more metadata features.
- the assignment function may then be arranged to assign different food candidates to different combinations of occurrences of the at least one image data feature and of occurrences of the at least one metadata feature.
- the already prepared food may comprise a variety of food components that have been prepared separately (e.g., a meat component and / or a side-dish component).
- a multiplicity of subsets of the image data for the corresponding multiplicity of food components can then be determined. This can be done using image analysis methods (in particular based on segmentation methods). Further, according to the method described in this document, based on the plurality of subsets of the image data, a plurality of recipes for the corresponding plurality of food components can be obtained. It is thus possible to find suitable recipes for complex dishes.
- the method may further comprise determining, based on the image data, environmental information regarding an environment of the already-prepared food.
- the environmental information may indicate which cutlery and / or dishes are being used for the food already prepared.
- the environment information can Thus, for example, give information regarding the consistency and / or the origin of the already produced food.
- the recipe can then be determined as a function of the environment information.
- the recognition rate of a recipe can be further increased.
- a system for determining a recipe for an already prepared food is described. This system is set up to obtain image data indicating the food already prepared. The system is further configured to determine, depending on the image data, a recipe, in particular a recipe suggestion for the already produced food.
- a software (SW) program is described.
- the SW program can be set up to run on a processor and thereby perform the method described in this document.
- a storage medium is described.
- the storage medium may include a SW program that is set up to run on a processor and thereby perform the method described in this document.
- Figure 1 is a block diagram of an exemplary system for determining a recipe for the production of a food.
- Figure 2 is a flow chart of an exemplary method for determining a recipe for the production of a food.
- FIG. 1 shows a block diagram of an exemplary system 100 for determining a recipe for a food 101.
- the food 101 typically includes a variety of different ingredients.
- food 101 may be cooked (e.g., cooked, fried, baked, grilled, etc.).
- the recipe to be determined includes a list of the ingredients of food 101 (and corresponding quantities).
- the recipe to be determined includes a list of process steps of a manufacturing process of the food 101.
- a user of the system 100 is enabled by the established recipe to produce the previously unknown food 101.
- the system 100 includes an electronic device 110 (e.g., a user's smartphone) configured to determine image data regarding the unknown, already-prepared food 101.
- the electronic device 1 10 may include a camera 1 1 1 configured to capture an image (and corresponding image data) from the food 101.
- the metadata can be determined by the electronic device, which display further information with regard to the image data.
- the metadata may include one or more of the following information:
- Location information e.g., GPS coordinates
- where e.g., in which country or region or restaurant
- Time information (eg a local time) that indicates at what time (eg at what local time of day) the image data was acquired.
- the image data 131 and possibly the metadata 132 can be transmitted to a recognition unit 120 (eg via a suitable wireless or wired communication connection).
- the recognition unit 120 is set up on the basis of the image data 131 and possibly on the basis of the metadata 132 to determine one or more food candidates to whom the food 101 represented in the image data 131 could correspond.
- the recognition unit 120 can access an assignment function which is set up to assign different food candidates to different characteristics of a feature vector.
- the assignment function may include, for example, a cluster algorithm, a support vector machine and / or a neural network.
- the recognition unit 120 may be configured to determine an expression of a feature vector for the food 101 to be determined on the basis of the image data 131 and possibly on the basis of the metadata 132.
- a feature vector may include a plurality of vector dimensions, wherein a vector dimension may describe a particular feature of the food 101.
- Exemplary features of the food 101 or of individual components of the food 101 are: color, texture, consistency, size, etc. The characteristics of such features may be determined based on the image data 131 (e.g., using image analysis techniques). This results in a feature vector describing features or properties (in this document also referred to as image data features) of the food 101 to be detected.
- the metadata 132 may be used to determine occurrences of other features of the feature vector (referred to herein as metadata features). Exemplary features that can be determined based on the metadata 132 are the location and / or time at which the food 101 to be detected was consumed. Alternatively or additionally, depending on the metadata 132, different assignment functions may be used to determine the one or more food candidates. By considering metadata 132, the quality (especially relevance) of the determined one or more food candidates can be increased.
- the assignment function 133 may be obtained from a local and / or remote food database 121. Access to a remote food database 121 may be via the Internet.
- the determination unit 120 can determine a list of one or more food candidates 135, which could be relevant for the determined expression of the feature vector. Furthermore, probabilities and / or relevance values for the one or more food candidates 135 may be determined. Thus, the one or more food candidates 135 may be selected with the relatively highest probability / relevance. Furthermore, the user may be provided with a list of one or more food candidates 135, possibly sorted by relevance. The list of one or more food candidates 135 may be communicated to the user's electronic device 110 for this purpose.
- the determination unit 120 is further configured to determine at least one recipe 134 for each of the one or more food candidates 135.
- the discovery unit 120 may access a local or remote recipe database 122 that provides at least one recipe 134 to a food candidate 135. Access to a remote recipe database 122 may be via the Internet.
- the determined recipes 134 for the one or more food candidates 135 can be transmitted to the electronic device 135 of the user and possibly displayed.
- the determination unit 120 may be configured to adjust the determination of food candidates 135 and / or recipes 134 in response to a feedback 136 from the user.
- an assignment function 133 can be adapted as a function of a feedback 136.
- the feedback 136 may indicate which candidate 135 of the identified food candidate 135 has been selected as correct by the user. This information may then be used in a machine learning procedure to adapt the assignment function 133 to determine the food candidates 135.
- the system 100 can be continuously improved.
- the system 100 is thus adapted to automatically detect a food 101 (especially a dish) based on a photograph.
- the photograph may be physical or digital, and may be provided in the form of suitable (digital) image data 131 for image analysis.
- the system 100 Based on the image data 131, the system 100 provides the user with suitable suggestions for recipes 134 (possibly with a probability indication for the individual suggestions).
- the recognition of a foodstuff 101 can take place not only through image recognition and image processing, but also through the inclusion of metadata 132 and possibly other data sources (eg country-specific exclusion criteria, national dish, etc. can be taken into account on the basis of the location information).
- the system 100 may be implemented as an application for a smartphone, as a plugin in a browser, etc.
- Detection of a food 101 may be adaptive (e.g., by interfacing with a knowledgeable expert system, such as the Watson system from IBM). Thereby, the recognition function of the system 100 can be automatically improved by the use of the system 100.
- a knowledgeable expert system such as the Watson system from IBM
- the photograph of the food 101 is digital (eg, in a collection of images or in a social media such as Facebook, Instagram, etc.) as image data 131.
- metadata 132 such as GPS data, timestamp, image description, etc.
- the system 100 may pre-filter based on the metadata 132 to restrict the list of possible food candidates.
- the GPS data shows in which country (eg India) the picture was taken. As a result, unlikely ingredients for this country (eg beef) can be excluded.
- based on the location information may be determined a restaurant in which the photo was taken. An online menu at the restaurant further restricts the list of potential food candidates.
- the date of taking a photo is known, it may be possible to compare it with a digital calendar of the user who created the photo to determine where the user was when the photo was taken. This information can then be used again to restrict the list of possible food candidates. Possibly. after the determination of a restricted list of possible food candidates, the image data of the image data 131 can be used to determine a list of (eg three) food candidates 135 having a relatively highest relevance value or match factor. Furthermore, suitable recipes 134 can be determined and made available to the user.
- the user may select one of the displayed recipes 134 and, if appropriate, provide feedback 136 (i.e., feedback) on the accuracy of a determined recipe 134.
- the feedback 136 may be used to enhance the recognition of food candidates 135 and / or recipes 134.
- the training data for teaching an expert system and / or an assignment function 133 can be increased, so that the recognition rate of the system 100 increases.
- information about a photograph of a food 101 may be provided based on external sources of information.
- An example of such an information source is a digital calendar of a user of the system 100, from which e.g. a typical whereabouts of the user can be determined. The typical location can be used to narrow the list of possible food candidates.
- features of the environment i.e. For example, the type of cutlery (e.g., knife and fork) with which food 101 is eaten may be determined. This information can be used to further reduce the list of potential food candidates.
- the system 100 may access a plurality of databases 121, 122 (possibly over the Internet). Via the databases 121, 122, information relating to recipes, country-specific properties, images of dishes, etc. can be determined.
- the method 200 includes determining 201 of image data 131 indicating the already-prepared food 101.
- a photograph of the food 101 may be provided.
- the digital data of the photo may correspond to the image data 131.
- the method 200 further comprises determining 202 a recipe 134 in dependence on the image data 131.
- a recipe 134 that was used with a certain probability for the production of the already produced food 101 can be determined.
- information regarding the likelihood or relevance of the determined recipe 134 may be provided.
- the image data 131 may be analyzed to determine one or more image data features from which one or more food candidates 135 may then be determined by a learned assignment function 133.
- Recipes 134 for the one or more food candidates 135 may then be identified and provided as possible recipes 134 for the already-prepared food 101 (e.g., by accessing a recipe database 122).
- the method 200 and / or system 100 described in this document enables a user to efficiently determine a recipe for an already-created food 101.
- the user is thereby enabled to make and / or share with himself an unknown food 101.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Analysis (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
Description
Claims
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
DE102015214060.1A DE102015214060A1 (de) | 2015-07-24 | 2015-07-24 | System und Verfahren zur Bereitstellung eines Rezeptes |
PCT/EP2016/066748 WO2017016886A1 (de) | 2015-07-24 | 2016-07-14 | System und verfahren zur bereitstellung eines rezeptes |
Publications (1)
Publication Number | Publication Date |
---|---|
EP3326109A1 true EP3326109A1 (de) | 2018-05-30 |
Family
ID=56609849
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
EP16747866.8A Withdrawn EP3326109A1 (de) | 2015-07-24 | 2016-07-14 | System und verfahren zur bereitstellung eines rezeptes |
Country Status (5)
Country | Link |
---|---|
US (1) | US10733479B2 (de) |
EP (1) | EP3326109A1 (de) |
CN (1) | CN107851183A (de) |
DE (1) | DE102015214060A1 (de) |
WO (1) | WO2017016886A1 (de) |
Families Citing this family (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE102015214060A1 (de) * | 2015-07-24 | 2017-01-26 | BSH Hausgeräte GmbH | System und Verfahren zur Bereitstellung eines Rezeptes |
US20190295440A1 (en) * | 2018-03-23 | 2019-09-26 | Nutrino Health Ltd. | Systems and methods for food analysis, personalized recommendations and health management |
US11672446B2 (en) | 2018-03-23 | 2023-06-13 | Medtronic Minimed, Inc. | Insulin delivery recommendations based on nutritional information |
CN111353333B (zh) * | 2018-12-21 | 2023-10-20 | 九阳股份有限公司 | 一种食材识别方法、家电设备及食材识别系统 |
CN110399804A (zh) * | 2019-07-01 | 2019-11-01 | 浙江师范大学 | 一种基于深度学习的食品检测识别方法 |
KR20210020702A (ko) * | 2019-08-16 | 2021-02-24 | 엘지전자 주식회사 | 인공지능 서버 |
US11663683B2 (en) | 2020-01-01 | 2023-05-30 | Rockspoon, Inc. | System and method for image-based food item, search, design, and culinary fulfillment |
Family Cites Families (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2010061382A (ja) * | 2008-09-03 | 2010-03-18 | Nikon Corp | 自動レシピ作成装置およびプログラム |
US8363913B2 (en) * | 2008-09-05 | 2013-01-29 | Purdue Research Foundation | Dietary assessment system and method |
CN202736122U (zh) * | 2012-08-20 | 2013-02-13 | 广西南宁推特信息技术有限公司 | 基于位置信息的营养食谱餐饮推荐系统 |
US20140104385A1 (en) * | 2012-10-16 | 2014-04-17 | Sony Network Entertainment International Llc | Method and apparatus for determining information associated with a food product |
US9230194B2 (en) * | 2013-09-16 | 2016-01-05 | Google Inc. | Training image sampling |
US9659225B2 (en) * | 2014-02-12 | 2017-05-23 | Microsoft Technology Licensing, Llc | Restaurant-specific food logging from images |
EP3221679A4 (de) * | 2014-11-21 | 2018-11-14 | Mutti, Christopher M. | Bildgebungssystem zur objekterkennung und beurteilung |
US10176642B2 (en) * | 2015-07-17 | 2019-01-08 | Bao Tran | Systems and methods for computer assisted operation |
DE102015214060A1 (de) * | 2015-07-24 | 2017-01-26 | BSH Hausgeräte GmbH | System und Verfahren zur Bereitstellung eines Rezeptes |
US10832302B2 (en) * | 2015-10-30 | 2020-11-10 | Forq, Inc. | Method for digital recipe library and food image recognition services |
US9519620B1 (en) * | 2016-01-29 | 2016-12-13 | International Business Machines Corporation | Identifying substitute ingredients using a natural language processing system |
WO2017135742A1 (ko) * | 2016-02-03 | 2017-08-10 | 주식회사 원더풀플랫폼 | 식재료 관리 시스템 및 식재료 관리 방법, 식재료를 이용한 레시피 제공 방법 및 이를 실행하는 서버, 식재료를 이용한 창작 레시피 생성방법 |
JP6843597B2 (ja) * | 2016-11-21 | 2021-03-17 | Nttテクノクロス株式会社 | 情報処理装置、食材選択方法及びプログラム |
US10671893B2 (en) * | 2016-12-05 | 2020-06-02 | Under Armour, Inc. | System and method for recipe to image associations |
WO2018165605A1 (en) * | 2017-03-09 | 2018-09-13 | Northwestern University | Hyperspectral imaging sensor |
US10856807B2 (en) * | 2017-06-29 | 2020-12-08 | Goddess Approved Productions, Llc | System and method for analyzing items using image recognition, optical character recognition, voice recognition, manual entry, and bar code scanning technology |
-
2015
- 2015-07-24 DE DE102015214060.1A patent/DE102015214060A1/de not_active Withdrawn
-
2016
- 2016-07-14 EP EP16747866.8A patent/EP3326109A1/de not_active Withdrawn
- 2016-07-14 CN CN201680043131.5A patent/CN107851183A/zh active Pending
- 2016-07-14 US US15/746,027 patent/US10733479B2/en active Active
- 2016-07-14 WO PCT/EP2016/066748 patent/WO2017016886A1/de active Application Filing
Also Published As
Publication number | Publication date |
---|---|
US10733479B2 (en) | 2020-08-04 |
WO2017016886A1 (de) | 2017-02-02 |
CN107851183A (zh) | 2018-03-27 |
DE102015214060A1 (de) | 2017-01-26 |
US20180211139A1 (en) | 2018-07-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2017016886A1 (de) | System und verfahren zur bereitstellung eines rezeptes | |
WO2020215985A1 (zh) | 医学影像分割方法、装置、电子设备和存储介质 | |
CN107679183B (zh) | 分类器用训练数据获取方法和装置、服务器及存储介质 | |
US10489633B2 (en) | Viewers and related methods, systems and circuits with patch gallery user interfaces | |
Ruiz et al. | An object-based approach for mapping forest structural types based on low-density LiDAR and multispectral imagery | |
CN114556413A (zh) | 用于组织分割的机器学习模型的交互式训练 | |
CN113537496A (zh) | 一种深度学习模型可视化构建系统及其应用和设计方法 | |
Seo et al. | Learning-based colorization of grayscale aerial images using random forest regression | |
Corbane et al. | Mapping natural habitats using remote sensing and sparse partial least square discriminant analysis | |
Bennett et al. | A transferable and effective method for monitoring continuous cover forestry at the individual tree level using UAVs | |
Amura et al. | Analysis of diagnostic images of artworks and feature extraction: design of a methodology | |
Barvir et al. | Developing versatile graphic map load metrics | |
CN108052918A (zh) | 一种笔迹比对系统及方法 | |
CN107562963B (zh) | 一种筛选家装设计渲染图的方法和装置 | |
CN110209916B (zh) | 一种兴趣点图像推荐方法及装置 | |
JP5973309B2 (ja) | 配信装置及びコンピュータプログラム | |
JP6842624B2 (ja) | 解析装置、解析方法、およびプログラム | |
Li et al. | Development of a single-leaf disease severity automatic grading system based on image processing | |
CN111291259B (zh) | 一种数据筛选方法、装置、电子设备和存储介质 | |
JP7380699B2 (ja) | 分析装置及びプログラム | |
Gaughan et al. | Using Very-High-Resolution Multispectral Classification to Estimate Savanna Fractional Vegetation Components | |
CN114882973A (zh) | 一种基于标准食品识别的每日营养摄取分析方法及系统 | |
DE102016013631A1 (de) | Modellieren von semantischen Konzepten in einem Einbettungsraum als Verteilungen | |
JP6931418B2 (ja) | 画像処理方法、画像処理装置、ユーザインタフェース装置、画像処理システム、サーバ、および画像処理プログラム | |
Bell et al. | Automated identification of multinucleated germ cells with U-Net |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE INTERNATIONAL PUBLICATION HAS BEEN MADE |
|
PUAI | Public reference made under article 153(3) epc to a published international application that has entered the european phase |
Free format text: ORIGINAL CODE: 0009012 |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE |
|
17P | Request for examination filed |
Effective date: 20180226 |
|
AK | Designated contracting states |
Kind code of ref document: A1 Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR |
|
AX | Request for extension of the european patent |
Extension state: BA ME |
|
DAV | Request for validation of the european patent (deleted) | ||
DAX | Request for extension of the european patent (deleted) | ||
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: EXAMINATION IS IN PROGRESS |
|
17Q | First examination report despatched |
Effective date: 20190607 |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: EXAMINATION IS IN PROGRESS |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE APPLICATION HAS BEEN WITHDRAWN |
|
18W | Application withdrawn |
Effective date: 20211221 |